Research map / Video / Video generation
Text-to-Any-Skeleton Motion Generation Without Retargeting
Qingyuan Liu, Ke Lv, Kun Dong, Jian Xue, Zehai Niu, Jinbao Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add K-GCA to SR-VAE (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | FID: 0.065 -> 0.027 | Improved |
| add K-GCA to SR-VAE (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Jitter Error: 9.594 -> 1.824 | Improved |
| use multi-head instead of single-head K-GCA (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | FID: 0.040 -> 0.027 | Improved |
| use multi-head instead of single-head K-GCA (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Jitter Error: 2.935 -> 1.824 | Improved |
| use multi-head instead of single-head K-GCA (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Skeleton Error: 12.294 -> 13.778 | Hurt |
| add residual vector quantization (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | FID: 0.165 -> 0.027 | Improved |
| add residual vector quantization (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Skeleton Error: 19.726 -> 13.778 | Improved |
| use asymmetric (different encoder/decoder skeleton) reconstruction instead of symmetric (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | FID: 0.885 -> 0.027 | Improved |
| use asymmetric reconstruction instead of symmetric (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Skeleton Error: 89.747 -> 13.778 | Improved |
| use MRO instead of rotation-based restoration (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Jitter Error: 30.724 -> 2.084 | Improved |
| use MRO instead of rotation-based restoration (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Skating Ratio: 0.193 -> 0.090 | Improved |
| add MRO over position-based restoration (ablation) | SR-VAE · SkeleMotion-3D test (random skeleton to HumanML3D skeleton) | Skeleton Error: 13.778 -> 0.00 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- AttT2M — AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism (ICCV 2023) · better on 1 of 1 shared result
- ReMoDiffuse — ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.88)
- SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing (CVPR 2025 · similarity 0.87)
- How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects (ICML 2025 · similarity 0.87)
- OmniMotionGPT: Animal Motion Generation with Limited Data (CVPR 2024 · similarity 0.87)
- TapMo: Shape-aware Motion Generation of Skeleton-free Characters (ICLR 2024 · similarity 0.87)
- HumanTOMATO: Text-aligned Whole-body Motion Generation (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
